AI/ML Engineering Journey
A structured, hands-on curriculum moving from machine learning foundations and neural networks to transformers, foundation models, applied AI, and ML systems.
Project overview
What I built
This repository documents an intentional AI/ML engineering path. The work progresses from mathematics and classical machine learning through deep learning, transformers, open-source models, fine-tuning, applied AI systems, and production-oriented ML infrastructure. The learning approach is simple: understand, implement, use, then integrate.
Category
AI/ML and Agents
Timeline
In progress since April 2026
Scope
14 technologies
Delivery notes
Highlights
The practical work, decisions, and working systems that shaped this project.
- Mathematics, classical machine learning, model evaluation, and scikit-learn
- Neural networks, backpropagation, autograd, deep learning, and PyTorch
- Transformers, tokenization, embeddings, attention, and foundation models
- LoRA and QLoRA fine-tuning, quantization, and model evaluation
- RAG, agents, tool calling, MCP, and orchestration for applied AI
- Model serving, MLOps, deployment, monitoring, computer vision, and edge AI
Technical foundation
Built with
The tools and platforms used to move the idea from concept to a working project.
Keep exploring
